Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2237 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.5935. Min Act: -0.0000

Data Index: 696825 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.3855. Min Act: -0.0000

Data Index: 1027195 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.1910. Min Act: -0.0000

Data Index: 834613 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.3280. Min Act: -0.0001

Data Index: 1230569 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.2156. Min Act: -0.0000

Data Index: 1086204 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.2289. Min Act: -0.0000

Data Index: 422176 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.1443. Min Act: -0.0000

Data Index: 1012954 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.0767. Min Act: -0.0000

Data Index: 255505 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.0436. Min Act: -0.0000

Data Index: 282133 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.1249. Min Act: -0.0000

Data Index: 139293 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.0250. Min Act: -0.0000

Data Index: 630328 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.0266. Min Act: -0.0000

Data Index: 317165 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 2.5935. Min Range: -2.5935

Max Act: 1.9979. Min Act: -0.0000

Data Index: 792958 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 2.5935. Min Range: -2.5935

Max Act: 1.9959. Min Act: -0.0000

Data Index: 464131 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 2.5935. Min Range: -2.5935

Max Act: 2.1128. Min Act: -0.0000

Data Index: 1501689 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 2.5935. Min Range: -2.5935

Max Act: 1.8614. Min Act: -0.0000

Data Index: 721289 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 2.5935. Min Range: -2.5935

Max Act: 1.8845. Min Act: -0.0000

Data Index: 195996 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 2.5935. Min Range: -2.5935

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1311388 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 2.5935. Min Range: -2.5935

Max Act: 1.9399. Min Act: -0.0000

Data Index: 1446546 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 2.5935. Min Range: -2.5935

Max Act: 1.9343. Min Act: -0.0000

Data Index: 479382 (C4 (Web Text))

Max Activating Token Index: 178